Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14270
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotion

    oai_token-act-pair · gpt-3.5-turbo

    the word "deeply" and its various contextual usages, indicating strong emotional sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.87
    ifully
    -0.78
    ulton
    -0.77
     Princ
    -0.75
    aily
    -0.69
    ulia
    -0.69
    igslist
    -0.68
    ammy
    -0.68
    imeters
    -0.68
    itatively
    -0.67
    POSITIVE LOGITS
     ingrained
    1.12
     saddened
    1.07
     rooted
    1.06
     regret
    0.97
     indebted
    0.95
     troubled
    0.94
     flawed
    0.94
     implicated
    0.93
     affected
    0.93
     offended
    0.92
    Activations Density 0.035%

    No Known Activations